Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 788 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6267. Min Act: -0.0001

Data Index: 1608289 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5525. Min Act: -0.0001

Data Index: 1436860 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4938. Min Act: -0.0001

Data Index: 1514827 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5150. Min Act: -0.0001

Data Index: 1585446 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4903. Min Act: -0.0001

Data Index: 1634829 (Python Code)

Max Activating Token Index: 862

Text #5

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4930. Min Act: -0.0001

Data Index: 1594372 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1508473 (Python Code)

Max Activating Token Index: 347

Text #7

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1638573 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5492. Min Act: -0.0001

Data Index: 1432476 (Python Code)

Max Activating Token Index: 393

Text #9

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1487088 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4522. Min Act: -0.0001

Data Index: 1458715 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4557. Min Act: -0.0001

Data Index: 1430436 (Python Code)

Max Activating Token Index: 602

Text #12

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4636. Min Act: -0.0001

Data Index: 1487044 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4406. Min Act: -0.0001

Data Index: 1385537 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4129. Min Act: -0.0001

Data Index: 1377706 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4164. Min Act: -0.0001

Data Index: 1638488 (Python Code)

Max Activating Token Index: 889

Text #16

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4399. Min Act: -0.0001

Data Index: 1537225 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4394. Min Act: -0.0001

Data Index: 1437254 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5039. Min Act: -0.0001

Data Index: 1525094 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1398912 (Python Code)

Max Activating Token Index: 20